Table 2 Descriptors selected by the genetic algorithm to differentiate chemicals with acidic and/or basic ionization sites
From: Open-source QSAR models for pKa prediction using multiple machine learning approaches
Name | Description |
|---|---|
minHBa | Minimum e-states for (strong) hydrogen bond acceptors |
minsOH | Minimum atom-type e-state: –OH |
TopoPSA | Topological polar surface area (TPSA) |
WTPT4 | Sum of path lengths starting from oxygens |
WTPT5 | Sum of path lengths starting from nitrogens |
SaaN | Sum of atom-type e-state: N |
SsOH | Sum of atom-type e-state: –OH |
minHBint2 | Minimum e-state descriptors of strength for potential hydrogen bonds of path length 2 |
AATS0i | Average Broto-Moreau autocorrelation − lag 0/weighted by first ionization potential |
ATSC1i | Centered Broto-Moreau autocorrelation − lag 1/weighted by first ionization potential |
maxHBa | Maximum e-states for (strong) hydrogen bond acceptors |
nHBAcc | Number of hydrogen bond acceptors (using CDK HBondAcceptorCountDescriptor algorithm) |
nHBint2 | Count of e-state descriptors of strength for potential hydrogen bonds of path length 2 |
ETA_dBeta | A measure of relative unsaturation content |
nHBDon_Lipinski | Number of hydrogen bond donors (using Lipinski’s definition: any OH or NH, each available hydrogen atom is counted as one hydrogen bond donor) |